© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41379
    Prev
    Next
    INDEX
    Explanations

    depth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     depth
    -1.54
     Depth
    -1.28
    depth
    -1.27
     profondeur
    -1.27
     ſind
    -1.25
     Efq
    -1.23
     Anſ
    -1.22
    BibitemShut
    -1.16
     houſe
    -1.15
     purpoſe
    -1.15
    POSITIVE LOGITS
     of
    0.77
     (
    0.69
    ,
    0.68
    -
    0.63
    .
    0.63
    to
    0.62
    ies
    0.62
     to
    0.60
     on
    0.60
     and
    0.60
    Activations Density 0.019%

    No Known Activations